The Known Good Updated 8 Oct 2026 Subscribe
Providers· Inference host· 36 tracked models

AtlasCloud — pricing & performance

Compare models All providers Data sources
Models served
36
of 1,191 tracked models
Mean output speed
61
tokens per second, averaged over
33 measured endpoints
Mean latency
1.8s
time to first token, averaged over
33 measured endpoints
Cheapest blended
$0.000
per 1M tokens at a 3:1
input:output blend
Output speed on AtlasCloud

Output tokens per second for the 33 of 36 models on AtlasCloud with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 36, measured or not. Higher is better. We do not run these measurements ourselves.

⇩
140
133
115
110
104
98
88
83
82
62
62
59
The Known Good
36 models on AtlasCloud
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V3.1 DeepSeek $0.30 $1.00 $0.47 54 1.2s 131k
DeepSeek: DeepSeek V3.1 Terminus DeepSeek $0.30 $1.00 $0.47 59 1.2s 131k
DeepSeek: DeepSeek V3.2 DeepSeek $0.26 $0.38 $0.29 41 0.9s 164k
DeepSeek: DeepSeek V3.2 Exp DeepSeek $0.13 $0.20 $0.15 30 1.5s 164k
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.14 $0.28 $0.17 83 1.5s 1.05M
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.44 $1.32 $0.66 62 2.6s 1.05M
DeepSeek: DeepSeek V4 Flash Vision Exp DeepSeek $0.44 $1.32 $0.66 31 4.8s 1.05M
DeepSeek: DeepSeek V4 Pro 0423 DeepSeek $1.68 $3.38 $2.10 43 1.7s 1.05M
DeepSeek: DeepSeek V4 Pro 0813 DeepSeek $1.32 $3.96 $1.98 46 1.4s 1.05M
DeepSeek: DeepSeek V4.1 Flash DeepSeek $0.30 $1.20 $0.53 110 1.2s 1.05M
Dots Studio: Dots3-Note Preview (free) dots-studio $0.000 $0.000 $0.000 54 1.3s 512k
Kwaipilot: KAT-Coder-Pro V2 Kuaishou $0.30 $1.20 $0.53 — — 262k
Kwaipilot: KAT-Coder-Pro V2.5 Kuaishou $0.74 $2.96 $1.29 — — 262k
Meituan: LongCat 2.0 meituan $0.30 $1.20 $0.53 50 1.7s 1.05M
MiniMax: MiniMax M2.5 MiniMax $0.29 $1.20 $0.52 82 1.4s 197k
MiniMax: MiniMax M2.7 MiniMax $0.30 $1.20 $0.53 40 1.6s 197k
MiniMax: MiniMax M3 MiniMax $0.30 $1.20 $0.53 115 2.6s 524k
MoonshotAI: Kimi K2.5 Moonshot AI $0.49 $2.50 $0.99 45 0.9s 262k
MoonshotAI: Kimi K2.6 Moonshot AI $0.95 $4.00 $1.71 98 1.2s 262k
MoonshotAI: Kimi K2.7 Code Moonshot AI $0.95 $4.00 $1.71 51 0.7s 262k
Qwen: Qwen3 235B A22B Instruct 2507 Alibaba $0.20 $0.88 $0.37 26 1.1s 131k
Qwen: Qwen3.5 397B A17B Alibaba $0.55 $3.50 $1.29 48 1.2s 262k
Qwen: Qwen3.5-122B-A10B Alibaba $0.30 $2.40 $0.82 133 1.0s 262k
Qwen: Qwen3.5-27B Alibaba $0.27 $2.16 $0.74 32 1.8s 262k
Qwen: Qwen3.5-35B-A3B Alibaba $0.23 $1.80 $0.62 104 1.3s 262k
Qwen: Qwen3.6 35B A3B Alibaba $0.19 $1.11 $0.42 140 0.9s 262k
Qwen: Qwen3.7 Max Alibaba $2.50 $7.50 $3.75 33 1.2s 1.00M
Tencent: Hy3 Tencent $0.20 $0.80 $0.35 88 2.2s 262k
Xiaomi: MiMo-V2.5-Pro Xiaomi $0.43 $0.87 $0.54 — — 1.02M
Z.ai: GLM 4.6 Z.ai $0.60 $2.20 $1.00 43 0.8s 203k
Z.ai: GLM 4.7 Z.ai $0.52 $1.85 $0.85 62 0.9s 203k
Z.ai: GLM 5 Z.ai $0.95 $3.15 $1.50 35 3.9s 203k
Z.ai: GLM 5.1 Z.ai $1.26 $3.96 $1.94 36 3.7s 203k
Z.ai: GLM 5.2 Z.ai $0.94 $2.95 $1.44 58 0.9s 1.05M
Z.ai: GLM 5.3 Z.ai $1.40 $4.40 $2.15 41 2.3s 1.05M
Z.ai: GLM 5.3 Flash Z.ai $0.15 $0.50 $0.24 41 5.3s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for AtlasCloud are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.